Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1375 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.9545. Min Act: 0.0000

Data Index: 1637678 (The Pile)

Max Activating Token Index: 547

Text #1

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.8733. Min Act: -0.0000

Data Index: 915088 (The Pile)

Max Activating Token Index: 108

Text #2

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.8474. Min Act: -0.0000

Data Index: 1906532 (The Pile)

Max Activating Token Index: 115

Text #3

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.7083. Min Act: -0.0000

Data Index: 1426103 (The Pile)

Max Activating Token Index: 12

Text #4

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.6677. Min Act: 0.0000

Data Index: 1984356 (The Pile)

Max Activating Token Index: 47

Text #5

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.7390. Min Act: -0.0000

Data Index: 1082605 (The Pile)

Max Activating Token Index: 787

Text #6

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.6460. Min Act: -0.0000

Data Index: 1066450 (The Pile)

Max Activating Token Index: 195

Text #7

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.6833. Min Act: -0.0000

Data Index: 908975 (The Pile)

Max Activating Token Index: 6

Text #8

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.6504. Min Act: -0.0000

Data Index: 413474 (The Pile)

Max Activating Token Index: 290

Text #9

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.5937. Min Act: -0.0000

Data Index: 269435 (The Pile)

Max Activating Token Index: 500

Text #10

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.6440. Min Act: -0.0000

Data Index: 61831 (The Pile)

Max Activating Token Index: 895

Text #11

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.6366. Min Act: 0.0000

Data Index: 1130982 (The Pile)

Max Activating Token Index: 98

Text #12

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.6203. Min Act: -0.0000

Data Index: 57872 (The Pile)

Max Activating Token Index: 87

Text #13

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.6174. Min Act: -0.0000

Data Index: 239297 (The Pile)

Max Activating Token Index: 488

Text #14

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.6573. Min Act: -0.0000

Data Index: 377340 (The Pile)

Max Activating Token Index: 640

Text #15

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.5894. Min Act: -0.0000

Data Index: 1876420 (The Pile)

Max Activating Token Index: 403

Text #16

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.5733. Min Act: 0.0000

Data Index: 4634 (The Pile)

Max Activating Token Index: 762

Text #17

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.6083. Min Act: -0.0000

Data Index: 1335814 (The Pile)

Max Activating Token Index: 755

Text #18

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.5841. Min Act: 0.0000

Data Index: 1865058 (The Pile)

Max Activating Token Index: 921

Text #19

Max Range: 0.9545. Min Range: -0.9545

Max Act: 0.5495. Min Act: 0.0000

Data Index: 319060 (The Pile)

Max Activating Token Index: 338